chemotools 0.1.1__py3-none-any.whl → 0.1.3__py3-none-any.whl

chemotools/smooth/{median_filter.py → _median_filter.py}

@@ -19,14 +19,6 @@ class MedianFilter(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
         The mode to use for the median filter. Can be "nearest", "constant", "reflect",
         "wrap", "mirror" or "interp". Default is "nearest".
 
-    Attributes
-    ----------
-    n_features_in_ : int
-        The number of features in the input data.
-
-    _is_fitted : bool
-        Whether the transformer has been fitted to data.
-
     Methods
     -------
     fit(X, y=None)
@@ -57,13 +49,7 @@ class MedianFilter(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
             The fitted transformer.
         """
         # Check that X is a 2D array and has only finite values
-        X = check_input(X)
-
-        # Set the number of features
-        self.n_features_in_ = X.shape[1]
-
-        # Set the fitted attribute to True
-        self._is_fitted = True
+        X = self._validate_data(X)
 
         return self
 
@@ -85,7 +71,7 @@ class MedianFilter(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
             The transformed data.
         """
         # Check that the estimator is fitted
-        check_is_fitted(self, "_is_fitted")
+        check_is_fitted(self, "n_features_in_")
 
         # Check that X is a 2D array and has only finite values
         X = check_input(X)

chemotools/smooth/{savitzky_golay_filter.py → _savitzky_golay_filter.py}

@@ -24,14 +24,6 @@ class SavitzkyGolayFilter(OneToOneFeatureMixin, BaseEstimator, TransformerMixin)
         The mode to use for the Savitzky-Golay filter. Can be "nearest", "constant",
         "reflect", "wrap", "mirror" or "interp". Default is "nearest".
 
-    Attributes
-    ----------
-    n_features_in_ : int
-        The number of features in the input data.
-
-    _is_fitted : bool
-        Whether the transformer has been fitted to data.
-
     Methods
     -------
     fit(X, y=None)
@@ -40,6 +32,7 @@ class SavitzkyGolayFilter(OneToOneFeatureMixin, BaseEstimator, TransformerMixin)
     transform(X, y=0, copy=True)
         Transform the input data by calculating the Savitzky-Golay filter.
     """
+
     def __init__(
         self, window_size: int = 3, polynomial_order: int = 1, mode: str = "nearest"
     ) -> None:
@@ -65,13 +58,7 @@ class SavitzkyGolayFilter(OneToOneFeatureMixin, BaseEstimator, TransformerMixin)
             The fitted transformer.
         """
         # Check that X is a 2D array and has only finite values
-        X = check_input(X)
-
-        # Set the number of features
-        self.n_features_in_ = X.shape[1]
-
-        # Set the fitted attribute to True
-        self._is_fitted = True
+        self._validate_data(X)
 
         return self
 
@@ -93,7 +80,7 @@ class SavitzkyGolayFilter(OneToOneFeatureMixin, BaseEstimator, TransformerMixin)
             The transformed data.
         """
         # Check that the estimator is fitted
-        check_is_fitted(self, "_is_fitted")
+        check_is_fitted(self, "n_features_in_")
 
         # Check that X is a 2D array and has only finite values
         X = check_input(X)

chemotools/smooth/{whittaker_smooth.py → _whittaker_smooth.py}

@@ -24,14 +24,6 @@ class WhittakerSmooth(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
     differences : int, optional
         The number of differences to use for the Whittaker smooth. Default is 1.
 
-    Attributes
-    ----------
-    n_features_in_ : int
-        The number of features in the input data.
-
-    _is_fitted : bool
-        Whether the transformer has been fitted to data.
-
     Methods
     -------
     fit(X, y=None)
@@ -66,13 +58,7 @@ class WhittakerSmooth(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
             The fitted transformer.
         """
         # Check that X is a 2D array and has only finite values
-        X = check_input(X)
-
-        # Set the number of features
-        self.n_features_in_ = X.shape[1]
-
-        # Set the fitted attribute to True
-        self._is_fitted = True
+        X = self._validate_data(X)
 
         return self
 
@@ -94,7 +80,7 @@ class WhittakerSmooth(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
             The transformed data.
         """
         # Check that the estimator is fitted
-        check_is_fitted(self, "_is_fitted")
+        check_is_fitted(self, "n_features_in_")
 
         # Check that X is a 2D array and has only finite values
         X = check_input(X)
@@ -113,14 +99,14 @@ class WhittakerSmooth(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
         return X_.reshape(-1, 1) if X_.ndim == 1 else X_
 
     def _calculate_whittaker_smooth(self, x):
-        X = np.matrix(x)
+        X = np.array(x)
         m = X.size
         E = eye(m, format="csc")
         w = np.ones(m)
         for i in range(self.differences):
             E = E[1:] - E[:-1]
         W = diags(w, 0, shape=(m, m))
-        A = csc_matrix(W + (self.lam * E.T * E))
-        B = csc_matrix(W * X.T)
+        A = csc_matrix(W + (self.lam * E.T @ E))
+        B = csc_matrix(W @ X.T).toarray().ravel()
         background = spsolve(A, B)
         return np.array(background)

{chemotools-0.1.1.dist-info → chemotools-0.1.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: chemotools
-Version: 0.1.1
+Version: 0.1.3
 Summary: Package to integrate chemometrics in scikit-learn pipelines
 Home-page: https://github.com/paucablop/chemotools
 Author: Pau Cabaneros Lopez

chemotools-0.1.3.dist-info/RECORD

@@ -0,0 +1,58 @@
+chemotools/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+chemotools/augmentation/__init__.py,sha256=LiYw-QE-cxiYY0ua4SOgL0sC_-uAjkykkcj7gRP8Mic,246
+chemotools/augmentation/baseline_shift.py,sha256=Zs0-3zHWaK26f2qGBRRMxA-q6FPxPG00g-8sHe61UAc,3213
+chemotools/augmentation/exponential_noise.py,sha256=X2HTpL9zoiu0cFq3VsTxS3x_IO_tA_DF2vJyKgh4_UA,3082
+chemotools/augmentation/index_shift.py,sha256=7ujZ_sz4mWEUJMDCHyaLxhTZ5-_K3nQPwtk6y6SLR9Q,3198
+chemotools/augmentation/normal_noise.py,sha256=NmzTuIJKyk6tfDJgmeX9iAzsKlJJk3984tS8nLLG9dg,3051
+chemotools/augmentation/spectrum_scale.py,sha256=WgMw_bCxWbyAYgYBO3q4PbbzcTDyBvVD73kxPfj3cdY,3174
+chemotools/augmentation/uniform_noise.py,sha256=gc0WdREItRiPHjNiZg79n0yK6bfntXkcImrEjkoRdus,3180
+chemotools/baseline/__init__.py,sha256=LFhsmzqv9RYxDS5-vK9jIf3ArNUSZ6yOF4SeUyVF6iA,381
+chemotools/baseline/_air_pls.py,sha256=bYAjemEWZr7oiYJegO0r5gtO16zr0BdJYjmEikA1yBc,5116
+chemotools/baseline/_ar_pls.py,sha256=tZi-89GMIStZUufz9AXVHU6TC1J6fAX4M1rAaIqgSvE,4431
+chemotools/baseline/_constant_baseline_correction.py,sha256=oxxzgCtnSHTEb9QczrxsmcHLtvCoKj6IQrH4M_5yNfw,3898
+chemotools/baseline/_cubic_spline_correction.py,sha256=pHpRdD6oVnn4BRg9CumlPJdAikG076kGjCU8mkMNpgw,3187
+chemotools/baseline/_linear_correction.py,sha256=DJow940emZQdcAKpCrkp7l5wyTYURLkr-hhHU6Pzlgw,3022
+chemotools/baseline/_non_negative.py,sha256=SyiS_-cfnypLXY3gC80oo7doqXUlHAAgmwrkRN4iNX8,2536
+chemotools/baseline/_polynomial_correction.py,sha256=0w9qA_w5dc9IIv5KMmAOZ06hWDuk-uyealsTaZX2qgw,3749
+chemotools/baseline/_subtract_reference.py,sha256=vfre6Z-bgDCwwl3VnpahmGJTBFJVK9HGBrUsjfl2O9o,3135
+chemotools/datasets/__init__.py,sha256=ojqxb-C_eDmizwUqVCJ8BqJxwULD7_hWCyVIA1uRO0c,116
+chemotools/datasets/_base.py,sha256=Z174CaIlpx17Yu8Pg1qZPuHWkS3BYWn7gtOYsoe8zNk,2895
+chemotools/datasets/data/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+chemotools/datasets/data/coffee_labels.csv,sha256=ZXQWQIf8faLHjdnHfRoXfxMR56kq9Q1BGPZBkQyhGlY,487
+chemotools/datasets/data/coffee_spectra.csv,sha256=VA-sN4u0hC5iALlRxxkj-K87Lz3b3mmUHBJPoDXychI,2206147
+chemotools/datasets/data/fermentation_hplc.csv,sha256=AMmiFQxwaXrH8aN310-3h1YQDiDrT8JNRv1RDvhEvg4,2140
+chemotools/datasets/data/fermentation_spectra.csv,sha256=MaaNMQP0lygJgFbEoUX0OUqdA-id8mF5Llvf_vj9tJk,15237508
+chemotools/datasets/data/train_hplc.csv,sha256=DjtmqiePOWB-F6TsOGFngE1pKyXkb7Xmsi-1CLxsTnE,249
+chemotools/datasets/data/train_spectra.csv,sha256=iVF19W52NHlbqq8BbLomn8n47kSPT0QxJv7wtQX4yjQ,203244
+chemotools/derivative/__init__.py,sha256=a9RAUYDG4C8VNJBbirRCpslKjEcKfRxUtSa39c3gp1s,86
+chemotools/derivative/_norris_william.py,sha256=NKmuo95vNWHQOdcww7APU9Z4s1wWExIRaj9O2Xrx8Bs,4753
+chemotools/derivative/_savitzky_golay.py,sha256=5At4sexJH0RvjkrvVfJvhIfaxXD3vE4Ozq1VClb3qlU,3417
+chemotools/feature_selection/__init__.py,sha256=p47SuyI7jMpV7kiaAsv2hA20smKf5Yo6447LfrNdDhY,76
+chemotools/feature_selection/_index_selector.py,sha256=2z2aAyMUOuP7x1n19RV5JGf6ZcM3mtJZby8tEgBOix4,3379
+chemotools/feature_selection/_range_cut.py,sha256=HI2OoeQYNph9uBICSA1cF2C_u-0UjTf0FDv5093tTnU,3223
+chemotools/scale/__init__.py,sha256=CQPUPx-8pUeHHbN9p5smFro3xtl_UEE0YeXHLVd7Lfk,118
+chemotools/scale/_min_max_scaler.py,sha256=-Wnr7zW-zmW6nR5J5yPdBm1KNuQDa9w27Un7rAr-s8E,2806
+chemotools/scale/_norm_scaler.py,sha256=bjMg1-x2I1xZmmbIgl4vXZZweJV-w3Euta0KGff_2Gk,2363
+chemotools/scale/_point_scaler.py,sha256=u2QELIHF35TReMk3RzXliacNPEAZJmVrjjJy9Rmn1q0,3256
+chemotools/scatter/__init__.py,sha256=-Zs5HBpPL3NaO25n8gh0JZI8f5z88cnt-kVFYT3s3a8,292
+chemotools/scatter/_extended_multiplicative_scatter_correction.py,sha256=SbTEMOPl3oWrzqIvYeVLrFhJKgPH9Ra32RO7OvzLJ00,6692
+chemotools/scatter/_multiplicative_scatter_correction.py,sha256=ZQaypqJhjmqSqW_f7SB_8qJxaHax1Jmz3hAs5fOves4,5547
+chemotools/scatter/_robust_normal_variate.py,sha256=DXHTVGx7rXRwoi-DDULN1CjA4gKv8dQDQ8giJ9X3oZs,2905
+chemotools/scatter/_standard_normal_variate.py,sha256=Q4Cr8aMp5u9pOSDFKM7NIRU5BSRbY7C2A_kDeNcOl4I,2377
+chemotools/smooth/__init__.py,sha256=x-QksF-Z_TIIRDR1EZMf44G0K1Fn7plofsufyaIwuvw,180
+chemotools/smooth/_mean_filter.py,sha256=D-v_GaNgAWxb2NTESVmAcSi-Nqw045hCvJRKLb5ksuc,2622
+chemotools/smooth/_median_filter.py,sha256=tDp_8JK2n9yVKeznf47vaYs8UTOt3D3p1f6PJpZpqy4,2638
+chemotools/smooth/_savitzky_golay_filter.py,sha256=gNIu7drl-Drb5WK0gBRlLu7AY_JHDIiiEDAEEAZJ8M4,3192
+chemotools/smooth/_whittaker_smooth.py,sha256=w9ZecU3A2SM0cWSGGGmYutE0KGpNgzln7w7ocao3nnU,3353
+chemotools/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+chemotools/utils/check_inputs.py,sha256=fRAV4HIaGamdj_PNXSNnl7LurXytACNTGO51rhPpMUY,512
+tests/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+tests/fixtures.py,sha256=Xa-Vd62Kd1fyWg3PLUSP6iIkOK8etrbyOkMJTn3dvX8,1933
+tests/test_datasets.py,sha256=_3mMDYC-vUnb5BenMqvuhmkHI2PPIdsyq_nNu2ggH20,1055
+tests/test_functionality.py,sha256=UhOYEShJZJOwROjNMf3UtXl5MrQBeQQbEMEt0ph7yQ0,21182
+tests/test_sklearn_compliance.py,sha256=CRB_0X9HRGj0pOpUCmiSHwJkCsVB-yK_apsyUONmfmw,5856
+chemotools-0.1.3.dist-info/LICENSE,sha256=qtyOy2wDQVX9hxp58h3T-6Lmfv-mSCHoSRkcLUdM9bg,1070
+chemotools-0.1.3.dist-info/METADATA,sha256=K_8Kuy1_hHBEK3p1WSMLfR0NfHuptAzCa5uijUT6RLc,5018
+chemotools-0.1.3.dist-info/WHEEL,sha256=Xo9-1PvkuimrydujYJAjF7pCkriuXBpUPEjma1nZyJ0,92
+chemotools-0.1.3.dist-info/top_level.txt,sha256=eNcNcKSdo-1H_2gwSDrS__dr7BM3R73Cnn-pBiW5FEw,17
+chemotools-0.1.3.dist-info/RECORD,,

{chemotools-0.1.1.dist-info → chemotools-0.1.3.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: bdist_wheel (0.41.2)
+Generator: bdist_wheel (0.41.3)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

tests/test_functionality.py

@@ -1,7 +1,8 @@
 import numpy as np
+import pandas as pd
 import pytest
 
-from chemotools.augmenation import (
+from chemotools.augmentation import (
     BaselineShift,
     ExponentialNoise, 
     IndexShift,
@@ -27,7 +28,7 @@ from chemotools.scatter import (
     StandardNormalVariate,
 )
 from chemotools.smooth import MeanFilter, MedianFilter, WhittakerSmooth
-from chemotools.variable_selection import RangeCut, SelectFeatures
+from chemotools.feature_selection import IndexSelector, RangeCut
 from tests.fixtures import (
     spectrum,
     spectrum_arpls,
@@ -231,6 +232,77 @@ def test_extended_baseline_correction_through_msc_median(spectrum):
 
     # Assert
     assert np.allclose(spectrum_emsc[0], spectrum_msc, atol=1e-8)
+    
+
+
+def test_index_selector():
+    # Arrange
+    spectrum = np.array([[1, 2, 3, 4, 5, 6, 7, 8, 9, 10]])
+
+    # Act
+    select_features = IndexSelector()
+    spectrum_corrected = select_features.fit_transform(spectrum)
+
+    # Assert
+    assert np.allclose(spectrum_corrected[0], spectrum[0], atol=1e-8)
+
+
+def test_index_selector_with_index():
+    # Arrange
+    spectrum = np.array([[1, 2, 3, 4, 5, 6, 7, 8, 9, 10]])
+    expected = np.array([[1, 2, 3, 8, 9, 10]])
+
+    # Act
+    select_features = IndexSelector(features=np.array([0, 1, 2, 7, 8, 9]))
+    spectrum_corrected = select_features.fit_transform(spectrum)
+
+    # Assert
+    assert np.allclose(spectrum_corrected[0], expected, atol=1e-8)
+
+
+def test_index_selector_with_wavenumbers():
+    # Arrange
+    wavenumbers = np.array([1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0])
+    spectrum = np.array([[1.0, 2.0, 3.0, 5.0, 8.0, 13.0, 21.0, 34.0, 55.0, 89.0]])
+    expected = np.array([[1.0, 2.0, 3.0, 34.0, 55.0, 89.0]])
+
+    # Act
+    select_features = IndexSelector(
+        features=np.array([1, 2, 3, 8, 9, 10]), wavenumbers=wavenumbers
+    )
+    spectrum_corrected = select_features.fit_transform(spectrum)
+
+    # Assert
+    assert np.allclose(spectrum_corrected[0], expected, atol=1e-8)
+
+
+def test_index_selector_with_wavenumbers_and_dataframe():
+    # Arrange
+    wavenumbers = np.array([1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0])
+    spectrum = pd.DataFrame(np.array([[1.0, 2.0, 3.0, 5.0, 8.0, 13.0, 21.0, 34.0, 55.0, 89.0]]))
+    expected = np.array([[1.0, 2.0, 3.0, 34.0, 55.0, 89.0]])
+
+    # Act
+    select_features = IndexSelector(
+        features=np.array([1, 2, 3, 8, 9, 10]), wavenumbers=wavenumbers
+    ).set_output(transform='pandas')
+
+    spectrum_corrected = select_features.fit_transform(spectrum)
+
+    # Assert
+    assert type(spectrum_corrected) == pd.DataFrame
+
+
+def test_index_shift():
+    # Arrange
+    spectrum = np.array([[1, 1, 1, 1, 1, 2, 1, 1, 1, 1]])
+    spectrum_shift = IndexShift(shift=1, random_state=42)
+
+    # Act
+    spectrum_corrected = spectrum_shift.fit_transform(spectrum)
+
+    # Assert
+    assert spectrum_corrected[0][4] == 2
 
 
 def test_l1_norm(spectrum):
@@ -539,7 +611,7 @@ def test_range_cut_by_wavenumber():
     assert np.allclose(spectrum_corrected[0], spectrum[0][1:7], atol=1e-8)
 
 
-def test_range_cut_by_wavenumber_2():
+def test_range_cut_by_wavenumber_with_list():
     # Arrange
     wavenumbers = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
     spectrum = np.array([[10, 12, 14, 16, 14, 12, 10, 12, 14, 16]])
@@ -552,6 +624,19 @@ def test_range_cut_by_wavenumber_2():
     assert np.allclose(spectrum_corrected[0], spectrum[0][1:7], atol=1e-8)
 
 
+def test_range_cut_by_wavenumber_with_dataframe():
+    # Arrange
+    wavenumbers = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
+    spectrum = pd.DataFrame(np.array([[10, 12, 14, 16, 14, 12, 10, 12, 14, 16]]))
+    range_cut = RangeCut(start=2.5, end=7.9, wavenumbers=wavenumbers).set_output(transform='pandas')
+
+    # Act
+    spectrum_corrected = range_cut.fit_transform(spectrum)
+
+    # Assert
+    assert type(spectrum_corrected) == pd.DataFrame
+
+
 def test_robust_normal_variate():
     # Arrange
     spectrum = np.array([2, 3.5, 5, 27, 8, 9]).reshape(1, -1)
@@ -608,59 +693,6 @@ def test_saviszky_golay_filter_3():
     assert np.allclose(spectrum_corrected[0], np.ones((1, 10)), atol=1e-2)
 
 
-def test_select_features():
-    # Arrange
-    spectrum = np.array([[1, 2, 3, 4, 5, 6, 7, 8, 9, 10]])
-
-    # Act
-    select_features = SelectFeatures()
-    spectrum_corrected = select_features.fit_transform(spectrum)
-
-    # Assert
-    assert np.allclose(spectrum_corrected[0], spectrum[0], atol=1e-8)
-
-
-def test_select_features_with_index():
-    # Arrange
-    spectrum = np.array([[1, 2, 3, 4, 5, 6, 7, 8, 9, 10]])
-    expected = np.array([[1, 2, 3, 8, 9, 10]])
-
-    # Act
-    select_features = SelectFeatures(features=np.array([0, 1, 2, 7, 8, 9]))
-    spectrum_corrected = select_features.fit_transform(spectrum)
-
-    # Assert
-    assert np.allclose(spectrum_corrected[0], expected, atol=1e-8)
-
-
-def test_select_features_with_wavenumbers():
-    # Arrange
-    wavenumbers = np.array([1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0])
-    spectrum = np.array([[1.0, 2.0, 3.0, 5.0, 8.0, 13.0, 21.0, 34.0, 55.0, 89.0]])
-    expected = np.array([[1.0, 2.0, 3.0, 34.0, 55.0, 89.0]])
-
-    # Act
-    select_features = SelectFeatures(
-        features=np.array([1, 2, 3, 8, 9, 10]), wavenumbers=wavenumbers
-    )
-    spectrum_corrected = select_features.fit_transform(spectrum)
-
-    # Assert
-    assert np.allclose(spectrum_corrected[0], expected, atol=1e-8)
-
-
-def test_index_shift():
-    # Arrange
-    spectrum = np.array([[1, 1, 1, 1, 1, 2, 1, 1, 1, 1]])
-    spectrum_shift = IndexShift(shift=1, random_state=42)
-
-    # Act
-    spectrum_corrected = spectrum_shift.fit_transform(spectrum)
-
-    # Assert
-    assert spectrum_corrected[0][4] == 2
-
-
 def test_spectrum_scale(spectrum):
     # Arrange
     spectrum_scale = SpectrumScale(scale=0.01, random_state=42)

tests/test_sklearn_compliance.py

@@ -1,6 +1,6 @@
 from sklearn.utils.estimator_checks import check_estimator
 
-from chemotools.augmenation import (
+from chemotools.augmentation import (
     BaselineShift,
     ExponentialNoise, 
     NormalNoise,
@@ -33,7 +33,7 @@ from chemotools.smooth import (
     SavitzkyGolayFilter,
     WhittakerSmooth,
 )
-from chemotools.variable_selection import RangeCut, SelectFeatures
+from chemotools.feature_selection import RangeCut, IndexSelector
 
 from tests.fixtures import spectrum
 
@@ -94,6 +94,14 @@ def test_compliance_extended_multiplicative_scatter_correction():
     check_estimator(transformer) 
 
 
+# IndexSelector
+def test_compliance_index_selector():
+    # Arrange
+    transformer = IndexSelector()
+    # Act & Assert
+    check_estimator(transformer)
+
+
 # IndexShift
 def test_compliance_spectrum_shift():
     # Arrange
@@ -197,6 +205,22 @@ def test_compliance_polynomial_correction():
     check_estimator(transformer)
 
 
+# RangeCut
+def test_compliance_range_cut():
+    # Arrange
+    transformer = RangeCut()
+    # Act & Assert
+    check_estimator(transformer)
+
+
+# RobustNormalVariate
+def test_compliance_robust_normal_variate():
+    # Arrange
+    transformer = RobustNormalVariate()
+    # Act & Assert
+    check_estimator(transformer)
+
+
 # SavitzkyGolay
 def test_compliance_savitzky_golay():
     # Arrange
@@ -213,14 +237,6 @@ def test_compliance_savitzky_golay_filter():
     check_estimator(transformer)
 
 
-# SelectFeatures
-def test_compliance_select_features():
-    # Arrange
-    transformer = SelectFeatures()
-    # Act & Assert
-    check_estimator(transformer)
-
-
 # SpectrumScale
 def test_compliance_spectrum_scale():
     # Arrange
@@ -237,21 +253,6 @@ def test_compliance_standard_normal_variate():
     check_estimator(transformer)
 
 
-# RangeCut
-def test_compliance_range_cut():
-    # Arrange
-    transformer = RangeCut()
-    # Act & Assert
-    check_estimator(transformer)
-
-
-# RobustNormalVariate
-def test_compliance_robust_normal_variate():
-    # Arrange
-    transformer = RobustNormalVariate()
-    # Act & Assert
-    check_estimator(transformer)
-
 # SubtractReference
 def test_compliance_subtract_reference():
     # Arrange

chemotools/augmenation/spectrum_shift.py

@@ -1,110 +0,0 @@
-import numpy as np
-from sklearn.base import BaseEstimator, TransformerMixin, OneToOneFeatureMixin
-from sklearn.utils.validation import check_is_fitted
-
-from chemotools.utils.check_inputs import check_input
-
-
-class SpectrumShift(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
-    """
-    Shift the spectrum a given number of indices.
-
-    Parameters
-    ----------
-    shift : float, default=1.0
-        Shifts the data by a random integer between -shift and shift.
-
-    random_state : int, default=None
-        The random state to use for the random number generator.
-    
-    Attributes
-    ----------
-    n_features_in_ : int
-        The number of features in the input data.
-
-    _is_fitted : bool
-        Whether the transformer has been fitted to data.
-    
-    Methods
-    -------
-    fit(X, y=None)
-        Fit the transformer to the input data.
-
-    transform(X, y=0, copy=True)
-        Transform the input data by shifting the spectrum.
-    """
-
-
-    def __init__(self, shift: int = 0.0, random_state: int = None):
-        self.shift = shift
-        self.random_state = random_state
-
-    def fit(self, X: np.ndarray, y=None) -> "SpectrumShift":
-        """
-        Fit the transformer to the input data.
-        
-        Parameters
-        ----------
-        X : np.ndarray of shape (n_samples, n_features)
-            The input data to fit the transformer to.
-
-        y : None
-            Ignored.
-
-        Returns
-        -------
-        self : PeakShift
-            The fitted transformer.
-        """
-        # Check that X is a 2D array and has only finite values
-        X = check_input(X)
-
-        # Set the number of features
-        self.n_features_in_ = X.shape[1]
-
-        # Set the fitted attribute to True
-        self._is_fitted = True
-
-        # Instantiate the random number generator
-        self._rng = np.random.default_rng(self.random_state)
-
-        return self
-
-    def transform(self, X: np.ndarray, y=None) -> np.ndarray:
-        """
-        Transform the input data by shifting the spectrum.
-
-        Parameters
-        ----------
-        X : np.ndarray of shape (n_samples, n_features)
-            The input data to transform.
-
-        y : None
-            Ignored.
-
-        Returns
-        -------
-        X_ : np.ndarray of shape (n_samples, n_features)
-            The transformed data.
-        """
-        # Check that the estimator is fitted
-        check_is_fitted(self, "_is_fitted")
-
-        # Check that X is a 2D array and has only finite values
-        X = check_input(X)
-        X_ = X.copy()
-
-        # Check that the number of features is the same as the fitted data
-        if X_.shape[1] != self.n_features_in_:
-            raise ValueError(f"Expected {self.n_features_in_} features but got {X_.shape[1]}")
-
-        # Calculate the standard normal variate
-        for i, x in enumerate(X_):
-            X_[i] = self._shift_spectrum(x)
-
-        return X_.reshape(-1, 1) if X_.ndim == 1 else X_
-
-    def _shift_spectrum(self, x) -> np.ndarray:
-        shift_amount = self._rng.integers(-self.shift, self.shift+1)
-        return np.roll(x, shift_amount)
-    

chemotools/variable_selection/__init__.py

@@ -1,2 +0,0 @@
-from .range_cut import RangeCut
-from .select_features import SelectFeatures

chemotools-0.1.1.dist-info/RECORD

@@ -1,59 +0,0 @@
-chemotools/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-chemotools/augmenation/__init__.py,sha256=LiYw-QE-cxiYY0ua4SOgL0sC_-uAjkykkcj7gRP8Mic,246
-chemotools/augmenation/baseline_shift.py,sha256=bazDs0FmowW_0al_xYuTZyUMdGmJ2YBkkFKuhFpkHN4,3215
-chemotools/augmenation/exponential_noise.py,sha256=X2HTpL9zoiu0cFq3VsTxS3x_IO_tA_DF2vJyKgh4_UA,3082
-chemotools/augmenation/index_shift.py,sha256=H0rQtjSP9SROqnVPh1k7WzwcaGAxPsaINsTVFB1O8eI,3111
-chemotools/augmenation/normal_noise.py,sha256=NmzTuIJKyk6tfDJgmeX9iAzsKlJJk3984tS8nLLG9dg,3051
-chemotools/augmenation/spectrum_scale.py,sha256=WgMw_bCxWbyAYgYBO3q4PbbzcTDyBvVD73kxPfj3cdY,3174
-chemotools/augmenation/spectrum_shift.py,sha256=vaenidCQnQ1WyMv8o-Yr5QdwNPAzAd1zDIKbK-suckU,3116
-chemotools/augmenation/uniform_noise.py,sha256=gc0WdREItRiPHjNiZg79n0yK6bfntXkcImrEjkoRdus,3180
-chemotools/baseline/__init__.py,sha256=W61mEZU_9-sVGRkP2MJOIhd6e9KsOS1BYjxm1NOMIyM,373
-chemotools/baseline/air_pls.py,sha256=qn03l66IrxW7woFbRmRqCmfZHzQ7KKW8A7ogTxTHKo0,5443
-chemotools/baseline/ar_pls.py,sha256=OY2cpU2X6KIBR9ag3PAJXo_uQbniIV58zbUJxCxvZWs,4736
-chemotools/baseline/constant_baseline_correction.py,sha256=97xpKOBOwT5EhrD5tf32ZfkyZpf0_bL-VtyUFng1hn4,4158
-chemotools/baseline/cubic_spline_correction.py,sha256=PCHqR7TAhbdlTZrxgedlk0PU0kRUwQd_jymh0g-ieo8,3311
-chemotools/baseline/linear_correction.py,sha256=6Sw2n4QTvIDKWRdJpFD48hMvOEwqbctUAQLF1WwcoXs,3381
-chemotools/baseline/non_negative.py,sha256=17_82l95U9kgoQ3Pdz3-jGv8B51JzqPdHODt6PegWRw,2864
-chemotools/baseline/polynomial_correction.py,sha256=caP866fwZb7PASyz6oezgg8hdZtFMT0EimK89TGSTSc,4059
-chemotools/baseline/subtract_reference.py,sha256=Pht87XadXK0URq2fun66OHaUk_cx56AkF84ta3VJy_8,3441
-chemotools/datasets/__init__.py,sha256=ojqxb-C_eDmizwUqVCJ8BqJxwULD7_hWCyVIA1uRO0c,116
-chemotools/datasets/_base.py,sha256=Z174CaIlpx17Yu8Pg1qZPuHWkS3BYWn7gtOYsoe8zNk,2895
-chemotools/datasets/data/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-chemotools/datasets/data/coffee_labels.csv,sha256=ZXQWQIf8faLHjdnHfRoXfxMR56kq9Q1BGPZBkQyhGlY,487
-chemotools/datasets/data/coffee_spectra.csv,sha256=VA-sN4u0hC5iALlRxxkj-K87Lz3b3mmUHBJPoDXychI,2206147
-chemotools/datasets/data/fermentation_hplc.csv,sha256=AMmiFQxwaXrH8aN310-3h1YQDiDrT8JNRv1RDvhEvg4,2140
-chemotools/datasets/data/fermentation_spectra.csv,sha256=MaaNMQP0lygJgFbEoUX0OUqdA-id8mF5Llvf_vj9tJk,15237508
-chemotools/datasets/data/train_hplc.csv,sha256=DjtmqiePOWB-F6TsOGFngE1pKyXkb7Xmsi-1CLxsTnE,249
-chemotools/datasets/data/train_spectra.csv,sha256=iVF19W52NHlbqq8BbLomn8n47kSPT0QxJv7wtQX4yjQ,203244
-chemotools/derivative/__init__.py,sha256=x2F0IJ-uCbEYFoXFbZl_RTPCbSq82vqGOwlM9R_2Klo,84
-chemotools/derivative/norris_william.py,sha256=JaJ7zlSiC_0tiITu7VWXtgKrmkQP7gLvuFb0_n1j9Dw,5081
-chemotools/derivative/savitzky_golay.py,sha256=fFzQRVGVXQIUkHp1x9dqfLVPlyStubIhSj9aGfZKuXY,3745
-chemotools/scale/__init__.py,sha256=HuXy_TktvXLTMWoW0pKhVCzMOkRkMRnvWCGiIKvjvZ8,115
-chemotools/scale/min_max_scaler.py,sha256=f1bGkODTWGwfnfMfWPimVxIZC3WIikgthQh-zUiaQUU,3123
-chemotools/scale/norm_scaler.py,sha256=qNs-npf5Jqcp8RYqt88_5-zwd-yIo-J1jItgUTFeozs,2699
-chemotools/scale/point_scaler.py,sha256=LGSmZwuEYLxzVPgH-_aRk9SjOdmyQTxdguqRdBfqCwc,3540
-chemotools/scatter/__init__.py,sha256=M0_B4hXVoDc2Qx00QreUfhFqPUTs6LbU4CWaFU17hg4,288
-chemotools/scatter/extended_multiplicative_scatter_correction.py,sha256=J65hyEFBzKNo_35Ta9MKWO35CjTw-8hDbSr8xd8RIfc,6912
-chemotools/scatter/multiplicative_scatter_correction.py,sha256=MFemiwS-KWFOtlcXVhLnY4mn6QQ8pttuj6UP0rodXEM,5689
-chemotools/scatter/robust_normal_variate.py,sha256=joIL-nGUja0nG8YcCuT32ehxmy2xOy3OD0t0yP5vWfM,3233
-chemotools/scatter/standard_normal_variate.py,sha256=wmK_8ea2CvoLaGebBFKr8zAU7QjGbaKAg04y6iZ4sDc,2681
-chemotools/smooth/__init__.py,sha256=Kwg3jVnl-W-efTHMR6-6hQsTp-An1lYQ1lZFj6sNMtg,176
-chemotools/smooth/mean_filter.py,sha256=fcC4EjO57Br3I9SJqWDJRxPxAv2WjjmXTECdBmBYXLI,2953
-chemotools/smooth/median_filter.py,sha256=5tR931HIej-yrw1SoV9t09gi55QKbZ3eCTeO-EjNSU8,2966
-chemotools/smooth/savitzky_golay_filter.py,sha256=OlkW4-gHsgk7HFf7yeweKkL6aOZpNqMSbUpvKjC66KY,3523
-chemotools/smooth/whittaker_smooth.py,sha256=OVEYEstsURgkLbjwRiBWeN_XNs_JOFeD60uyZsVtrHQ,3664
-chemotools/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-chemotools/utils/check_inputs.py,sha256=fRAV4HIaGamdj_PNXSNnl7LurXytACNTGO51rhPpMUY,512
-chemotools/variable_selection/__init__.py,sha256=6gKxCAoGKAOhhTerUyBg_62YKCIr0K4mbDcoDfbMJeA,75
-chemotools/variable_selection/range_cut.py,sha256=1uH_nwYXEn_N1NY14n4uXpVvO6VVpM8zHea1cbHyZu4,4141
-chemotools/variable_selection/select_features.py,sha256=pcoFmGZLUPjtRytGpnqK8YdVj3Z5hwKGSJ10VxCpg58,4164
-tests/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-tests/fixtures.py,sha256=Xa-Vd62Kd1fyWg3PLUSP6iIkOK8etrbyOkMJTn3dvX8,1933
-tests/test_datasets.py,sha256=_3mMDYC-vUnb5BenMqvuhmkHI2PPIdsyq_nNu2ggH20,1055
-tests/test_functionality.py,sha256=b71JDPjrOJkAp1F-2TV-iWfftol46066y_jGxL8LN5I,20119
-tests/test_sklearn_compliance.py,sha256=vMHOfayAwtj9GVkbB0rIwhZzFTZBekwqvgY6zy6GTzA,5859
-chemotools-0.1.1.dist-info/LICENSE,sha256=qtyOy2wDQVX9hxp58h3T-6Lmfv-mSCHoSRkcLUdM9bg,1070
-chemotools-0.1.1.dist-info/METADATA,sha256=h-BS9J_XWlbr10p_EVKtoJsgCtPbGZSgx2d3cpdjGlY,5018
-chemotools-0.1.1.dist-info/WHEEL,sha256=yQN5g4mg4AybRjkgi-9yy4iQEFibGQmlz78Pik5Or-A,92
-chemotools-0.1.1.dist-info/top_level.txt,sha256=eNcNcKSdo-1H_2gwSDrS__dr7BM3R73Cnn-pBiW5FEw,17
-chemotools-0.1.1.dist-info/RECORD,,